English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce the submissions of the NJUNLP team to the WMT 2023 QualityEstimation (QE) shared task. Our team submitted predictions for theEnglish-German language pair on all two sub-tasks: (i) sentence- and word-levelquality prediction; and (ii) fine-grained error span detection. This year, wefurther explore pseudo data methods for QE based on NJUQE framework(https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using paralleldata from the WMT translation task. We pre-train the XLMR large model on pseudoQE data, then fine-tune it on real QE data. At both stages, we jointly learnsentence-level scores and word-level tags. Empirically, we conduct experimentsto find the key hyper-parameters that improve the performance. Technically, wepropose a simple method that covert the word-level outputs to fine-grainederror span results. Overall, our models achieved the best results inEnglish-German for both word-level and fine-grained error span detectionsub-tasks by a considerable margin.

Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task